CN114323035A - Positioning method, device and system - Google Patents

Abstract

The present application provides a positioning method, device and system. After the vehicle is started, the sensing information of the vehicle is obtained according to the time interval. When the vehicle is positioned, the sensing information corresponding to the current moment is obtained through the vehicle-mounted sensing device, and the sensing information corresponding to the current moment is obtained at the time of the vehicle positioning. The sensor information obtained at the critical moment, so as to locate the vehicle according to the obtained sensor information and the map information of the area where the vehicle is located. Since the present application acquires the sensing information from the time dimension, the process of acquiring the sensing information is not affected by road congestion, so that the sensing information used for positioning can be updated according to the time interval when the vehicle is running, thereby improving the accuracy of positioning. accuracy. In addition, the sensory information is obtained from the time dimension. When the vehicle is running at a low speed, the environmental information around the vehicle can be collected in the gap between the vehicles. At this time, due to the slow speed of the vehicle, the collected environmental information around the vehicle is clearer. Further Improve positioning accuracy.

Description

Positioning method, device and system

technical field

The embodiments of the present application relate to the technical field of intelligent driving, and in particular, to a positioning method, device, and system.

Background technique

Lidar, as an unmanned driving vehicle positioning sensor, works with image recognition and other technologies to realize the perception of the surrounding environment and the global positioning of the vehicle. Among them, the methods of installing lidar on the vehicle include a roof laser installation method and a front protection installation method.

Among them, the front protection installation method installs the lidar on the front and both sides of the vehicle. The installation position is low and easily blocked, resulting in a small sensing range, resulting in less information for positioning, resulting in inaccurate positioning. Therefore, in order to improve the accuracy of positioning, the lidar is controlled to collect environmental information around the vehicle every time the vehicle travels a preset distance. During vehicle positioning, positioning is performed according to the environmental information around the vehicle collected multiple times, and the positioning accuracy is high.

However, when the road is congested, the vehicle travels slowly, and the environmental information around the vehicle cannot be collected in time. As a result, when the vehicle is positioned, the environmental information around the vehicle collected multiple times for positioning is not updated, resulting in poor positioning accuracy.

SUMMARY OF THE INVENTION

The present application provides a positioning method, device and system, aiming at solving the problem of inaccurate vehicle positioning caused by obstructions, road congestion and the like.

In a first aspect, the present application provides a positioning method, which can be implemented by a vehicle or a component in the vehicle, such as a processing device, circuit, chip and other components in the vehicle, or for communicating with the vehicle through a gateway. cloud server. The method includes:

At the current moment, the first sensing information is obtained through the vehicle-mounted sensing device, and the first sensing information includes the coordinates of the feature points in the vehicle body coordinate system and the vehicle position in the vehicle body coordinate system collected by the vehicle-mounted sensing device at the current moment. the odometer information at the current moment;

Acquiring second sensing information obtained by the vehicle-mounted sensing device at a critical moment, where the second sensing information includes the coordinates of the feature points in the vehicle body coordinate system collected by the vehicle-mounted sensing device at the critical moment and the odometer information of the vehicle at the critical moment, wherein the critical moment includes a first critical moment, and the first critical moment is the moment when the second sensing information is acquired according to the time interval, and the first critical moment The time interval between the moment and the current moment is less than or equal to the preset duration;

The position of the vehicle at the current moment is determined according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information.

In a possible implementation manner, the determining the position of the vehicle at the current moment according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information includes:

According to the odometer information in the first sensing information and the odometer information in the second sensing information, the coordinates of the feature points collected at the critical moment are mapped to the vehicle body coordinate system at the current moment , obtain the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment;

The position of the vehicle at the current moment is determined according to the feature points collected at the critical moment and the coordinates of the feature points collected at the current moment in the vehicle body coordinate system at the current moment, respectively, and the map information.

In a possible implementation manner, the determination of the The position of the vehicle at the current moment, including:

At the current moment, for each of the M particles corresponding to the vehicle, according to the feature points collected at the critical moment and the feature points collected at the current moment, respectively, under the vehicle body coordinate system at the current moment coordinates and the position of each particle to obtain the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information, wherein the M particles are the last time the vehicle was positioned The particle used, the position of each particle is based on the odometer information at the last time the vehicle was positioned, the odometer information at the current moment, and the position of each particle at the last time the vehicle was positioned. position obtained, M is a positive integer;

According to the matching degree of each of the M particles at the current moment and the M particles, obtain K particles, where K is a positive integer;

The position of the vehicle at the current moment is obtained according to the positions of the K particles corresponding to the vehicle at the current moment.

In a possible implementation manner, the coordinates of the feature points collected according to the critical moment and the feature points collected at the current moment are respectively the coordinates of the vehicle body coordinate system at the current moment and the position of each particle, Obtain the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information, including:

mapping the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with the particle as the origin;

The matching degree between the target object to be matched and the corresponding target object in the map information, which is mapped to the current moment in the particle coordinate system and the feature points collected at the critical moment, is obtained.

In a possible implementation manner, obtaining K particles according to the matching degree of each of the M particles at the current moment and the M particles, including:

Acquire L particles whose matching degree is greater than or equal to a preset matching degree among the M particles, where L is less than or equal to M and less than or equal to K;

Determining the L particles as the K particles; or,

obtaining at least one particle from the L particles;

The K particles are obtained from the L particles and the at least one particle.

In a possible implementation manner, the obtaining the K particles according to the L particles and the at least one particle includes:

copying each particle at least once according to the matching degree of each particle in the at least one particle;

The L particles and the particles obtained after replication are determined as the K particles.

In a possible implementation manner, the obtaining the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment includes:

According to the position of each of the K particles, the average position of the K particles is obtained, and the average position of the K particles is determined as the position of the vehicle at the current moment.

In a possible implementation, the method further includes:

According to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, an evaluation value of the position of the vehicle at the current moment is obtained, and the evaluation value indicates the position of the vehicle at the current moment. The difference between the position of the vehicle at the current moment and the real position information of the vehicle at the current moment.

In a possible implementation manner, according to the odometer information in the second sensing information and the odometer information in the second sensing information, the coordinates of the feature points collected at the critical moment are respectively Map to the vehicle body coordinate system at the current moment, and obtain the coordinates of the feature points collected at the critical moment under the vehicle body coordinate system at the current moment, including:

According to the mileage information in the first sensing information and the mileage information in the second sensing information, determine the difference between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first critical moment Coordinate mapping relationship;

According to the coordinate mapping relationship, the coordinates of the feature points collected at the first critical moment are respectively mapped to the vehicle body coordinate system at the current moment, and the feature points collected at the first critical moment are obtained at the current moment. The coordinates in the vehicle body coordinate system.

In a possible implementation manner, the critical moment further includes a second critical moment, and the second critical moment is the moment at which the second sensing information is acquired according to the distance interval, wherein the vehicle receives the second critical moment from the second critical moment. The driving distance from the position at the moment to the position corresponding to the current moment is less than or equal to the preset distance.

In a possible implementation manner, the determining the position of the vehicle at the current moment according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information includes:

According to the map information and the first sensing information and the second sensing information, the pose of the vehicle at the current moment is determined.

In a possible implementation manner, the coordinates of the feature points collected according to the critical moment and the feature points collected at the current moment are respectively the coordinates of the vehicle body coordinate system at the current moment and the position of each particle, Before obtaining the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information, the method further includes:

Determine the target feature point according to the feature points collected at each critical moment and the feature value of each feature point in the feature points collected at the current moment;

According to the feature points collected at each critical moment and the feature values of the feature points collected at the current moment except the feature points included in the feature point set, the target feature point is determined again, and the feature point set includes The feature points are the feature points located within the preset distance range of the target feature point determined last time and the target feature point determined last time;

When the number of the target feature points satisfies the preset number, N target feature points are obtained, and the N is equal to the preset number;

According to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment respectively in the vehicle body coordinate system at the current moment and the position of each particle, the current moment and the collection of the critical moment are obtained. The matching degree between the feature points of and the target object in the map information, including:

According to the coordinates of the N target feature points in the vehicle body coordinate system at the current moment and the position of each particle, the feature points collected at the current moment and the critical moment and the map information of the target area are obtained the matching degree of the target.

In a possible implementation manner, the eigenvalues of the feature points are obtained through an evaluation function, and the eigenvalues are used to evaluate the stability of the feature points.

In a possible implementation manner, the target feature point is the feature point with the largest feature value among the feature points.

In a possible implementation, the origin of the vehicle body coordinate system is located at any position on the vehicle.

In a second aspect, the present application provides a positioning device, comprising:

The acquisition module is used to acquire first sensing information through the vehicle-mounted sensing device at the current moment, where the first sensing information includes the feature points collected by the vehicle-mounted sensing device at the current moment in the vehicle body coordinate system The coordinates of the vehicle and the odometer information of the vehicle at the current moment; it is also used to acquire the second sensing information obtained by the vehicle-mounted sensing device at a critical moment, and the second sensing information includes the vehicle-mounted sensing device The coordinates of the feature points in the vehicle body coordinate system collected at the critical moment and the odometer information of the vehicle at the critical moment, wherein the critical moment includes a first critical moment, and the first critical moment is The moment when the second sensing information is acquired according to the time interval, the time interval between the first critical moment and the current moment is less than or equal to a preset duration;

The positioning module is configured to determine the position of the vehicle at the current moment according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information.

In a possible implementation manner, when the positioning module determines the position of the vehicle at the current moment according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information, it specifically uses At:

According to the odometer information in the first sensing information and the odometer information in the second sensing information, the coordinates of the feature points collected at the critical moment are mapped to the vehicle body coordinate system at the current moment , obtain the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment;

The position of the vehicle at the current moment is determined according to the feature points collected at the critical moment and the coordinates of the feature points collected at the current moment in the vehicle body coordinate system at the current moment, respectively, and the map information.

In a possible implementation manner, the positioning module determines, according to the feature points collected at a critical moment and the coordinates of the feature points collected at the current moment in the vehicle body coordinate system at the current moment, and the map information, respectively, When the vehicle is at the position of the current moment, it is specifically used for:

At the current moment, for each of the M particles corresponding to the vehicle, according to the feature points collected at the critical moment and the feature points collected at the current moment, respectively, under the vehicle body coordinate system at the current moment coordinates and the position of each particle to obtain the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information, wherein the M particles are the last time the vehicle was positioned The particle used, the position of each particle is based on the odometer information at the last time the vehicle was positioned, the odometer information at the current moment, and the position of each particle at the last time the vehicle was positioned. position obtained, M is a positive integer;

According to the matching degree of each of the M particles at the current moment and the M particles, obtain K particles, where K is a positive integer;

The position of the vehicle at the current moment is obtained according to the positions of the K particles corresponding to the vehicle at the current moment.

In a possible implementation manner, the positioning module is based on the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the coordinates of each particle respectively. When obtaining the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information, it is specifically used for:

mapping the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with the particle as the origin;

The matching degree between the target object to be matched and the corresponding target object in the map information, which is mapped to the current moment in the particle coordinate system and the feature points collected at the critical moment, is obtained.

In a possible implementation manner, when the positioning module obtains K particles according to the matching degree of each of the M particles and the M particles at the current moment, it is specifically used for:

Acquire L particles whose matching degree is greater than or equal to a preset matching degree among the M particles, where L is less than or equal to M and less than or equal to K;

Determining the L particles as the K particles; or,

obtaining at least one particle from the L particles;

The K particles are obtained from the L particles and the at least one particle.

In a possible implementation manner, when the positioning module obtains the K particles according to the L particles and the at least one particle, it is specifically used for:

copying each particle at least once according to the matching degree of each particle in the at least one particle;

The L particles and the particles obtained after replication are determined as the K particles.

In a possible implementation manner, when obtaining the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment, the positioning module is specifically used for:

According to the position of each of the K particles, the average position of the K particles is obtained, and the average position of the K particles is determined as the position of the vehicle at the current moment.

In a possible implementation manner, the positioning module is further used for:

According to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, an evaluation value of the position of the vehicle at the current moment is obtained, and the evaluation value indicates the position of the vehicle at the current moment. The difference between the position of the vehicle at the current moment and the real position information of the vehicle at the current moment.

In a possible implementation manner, the positioning module, according to the odometer information in the second sensing information and the odometer information in the second sensing information, The coordinates are respectively mapped to the vehicle body coordinate system at the current moment, and when the coordinates of the feature points collected at the critical moment under the vehicle body coordinate system at the current moment are obtained, it is specifically used for:

According to the mileage information in the first sensing information and the mileage information in the second sensing information, determine the difference between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first critical moment Coordinate mapping relationship;

According to the coordinate mapping relationship, the coordinates of the feature points collected at the first critical moment are respectively mapped to the vehicle body coordinate system at the current moment, and the feature points collected at the first critical moment are obtained at the current moment. The coordinates in the vehicle body coordinate system.

In a possible implementation manner, the critical moment further includes a second critical moment, and the second critical moment is the moment at which the second sensing information is acquired according to the distance interval, wherein the vehicle receives the second critical moment from the second critical moment. The driving distance from the position at the moment to the position corresponding to the current moment is less than or equal to the preset distance.

In a possible implementation manner, when the positioning module determines the position of the vehicle at the current moment according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information, it specifically uses At:

According to the map information and the first sensing information and the second sensing information, the pose of the vehicle at the current moment is determined.

In a possible implementation manner, the positioning module is based on the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment in the vehicle body coordinate system at the current moment and the coordinates of each particle respectively. Before obtaining the matching degree between the feature points collected at the current moment and the critical moment and the target object in the map information, it is also used for:

Determine the target feature point according to the feature points collected at each critical moment and the feature value of each feature point in the feature points collected at the current moment;

According to the feature points collected at each critical moment and the feature values of the feature points collected at the current moment except the feature points included in the feature point set, the target feature point is determined again, and the feature point set includes The feature points are the feature points located within the preset distance range of the target feature point determined last time and the target feature point determined last time;

When the number of the target feature points satisfies the preset number, N target feature points are obtained, and the N is equal to the preset number;

The positioning module obtains the current moment and the key according to the coordinates of the feature points collected at the critical moment and the feature points collected at the current moment respectively in the vehicle body coordinate system at the current moment and the position of each particle. When the matching degree between the feature points collected at all times and the target object in the map information, it is specifically used for:

According to the coordinates of the N target feature points in the vehicle body coordinate system at the current moment and the position of each particle, the feature points collected at the current moment and the critical moment and the map information of the target area are obtained the matching degree of the target.

In a possible implementation manner, the eigenvalues of the feature points are obtained through an evaluation function, and the eigenvalues are used to evaluate the stability of the feature points.

In a possible implementation manner, the target feature point is the feature point with the largest feature value among the feature points.

In a possible implementation, the origin of the vehicle body coordinate system is located at any position on the vehicle.

In a third aspect, the present application provides a positioning device, comprising: a memory and at least one processor;

the memory for storing program instructions;

The processor is configured to call the program instructions in the memory to execute the positioning method according to any one of the first aspect.

In a fourth aspect, the present application provides a positioning system, including a vehicle and a vehicle-mounted sensing device;

the vehicle-mounted sensing device is mounted on the vehicle;

the vehicle, configured to execute the positioning method according to any one of the first aspects; or,

The in-vehicle sensing device is configured to execute the positioning method according to any one of the first aspects.

In a fifth aspect, the present application provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause the computer to execute the positioning method according to any one of the first aspects.

In a sixth aspect, the present application provides a program product, the program product includes a computer program, the computer program is stored in a readable storage medium, and at least one processor of the positioning device can read the data from the readable storage medium. The computer program is executed by the at least one processor so that the positioning apparatus implements the positioning method according to any one of the first aspects.

The present application provides a positioning method, device and system. After the vehicle is started, the sensing information of the vehicle is acquired according to the time interval, and when the vehicle is positioned, the first sensing information corresponding to the current moment and the first sensing information corresponding to at least one critical moment are acquired. Second sensing information, the vehicle is positioned according to the first sensing information, the at least one second sensing information and the map information. Since the sensing information is obtained from the time dimension, the process of obtaining the sensing information is not affected by road congestion, so that the sensing information used for positioning can be updated according to the time interval when the vehicle is running, thereby improving the accuracy of positioning. Moreover, the sensor information is obtained from the time dimension. When the vehicle is running at a low speed, the environmental information around the vehicle can be collected in the gap between the vehicles. At this time, due to the slow speed of the vehicle, the collected environmental information around the vehicle is clearer. To further improve the accuracy of positioning.

Description of drawings

FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

FIG. 2 is a flowchart of a positioning method provided by an embodiment of the present application

3 is a schematic diagram of a vehicle body coordinate system provided by an embodiment of the present application;

4 is a schematic diagram of positioning a vehicle according to an embodiment of the present application;

5 is a schematic diagram of positioning a vehicle according to another embodiment of the present application;

6 is a schematic diagram of positioning a vehicle according to another embodiment of the present application;

7a is a schematic diagram of surrounding environment information when a vehicle faces a first direction according to an embodiment of the application;

FIG. 7b is a schematic diagram of surrounding environment information when a vehicle faces a second direction according to an embodiment of the application;

8 is a flowchart of a positioning method provided by another embodiment of the present application;

9 is a flowchart of a positioning method provided by another embodiment of the present application;

FIG. 10 is a schematic diagram of particle initialization provided by an embodiment of the present application;

11 is a schematic diagram of surrounding environment information in a vehicle body coordinate system and a particle coordinate system, respectively, provided by an embodiment of the application;

12 is a schematic structural diagram of a positioning device provided by an embodiment of the application;

13 is a schematic structural diagram of a positioning device provided by an embodiment of the application;

FIG. 14 is a schematic structural diagram of a positioning system according to an embodiment of the present application.

Detailed ways

To facilitate understanding of the embodiments of the present application, concepts involved in the embodiments of the present application are first introduced.

Current moment: The moment when the vehicle starts positioning.

Critical moment: After the vehicle is started, the sensor device scans the surrounding environment information of the vehicle, and the scanned surrounding environment information of the vehicle is used for positioning.

Feature point: The point cloud corresponding to the surrounding environment of the vehicle scanned by the sensor device can reflect the characteristics of the target in the surrounding environment. Therefore, the target in the surrounding environment can be identified by the feature points.

FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application. In the intelligent driving mode of the vehicle, after the vehicle is started, for example, the vehicle is driving, or temporarily stopped due to congestion, waiting for traffic lights, etc., the vehicle's surrounding environment information is sensed through lidar to locate the vehicle. Specifically: setting a preset distance, the lidar on the vehicle emits a laser signal around the vehicle every time the vehicle travels a preset distance. After the target in the surrounding environment of the vehicle is scanned by the laser, it is displayed as a cloud of points. The sign information around the vehicle is extracted by acquiring the point cloud at each acquisition. During positioning, the vehicle positioning is realized by matching the sign information around the vehicle collected multiple times with the map information.

However, when the vehicle is driving on a congested road, the driving is slow, so that the vehicle cannot update the collected surrounding environmental information in time when positioning the vehicle, resulting in inaccurate positioning.

For example, as shown in Figure 1, when the vehicle is driving on a congested road, the environmental information around the vehicle is collected every 100 meters. For example, the vehicle collects the surrounding information at points A, B, C and D respectively. Environmental information, when the vehicle travels to point E, since the driving distance between point D and point E is less than 100 meters, when point E needs to be positioned, the environmental information around the vehicle is collected according to point A, point B, point C and point D Positioning is performed. At this time, due to the existence of errors, the position of the vehicle positioning is located in the vicinity of point D.

Due to road congestion, the vehicle travels slowly, and when the vehicle reaches point F and needs to be positioned, the driving distance between point D and point F is still less than 100 meters, so that the environmental information around the vehicle collected by the vehicle is still at point A, Collected at points B, C and D. Therefore, during positioning, the environment information around the vehicle is still collected according to points A, B, C and D for positioning, resulting in a large difference between the position of the vehicle obtained through positioning and the real position of the vehicle, and the positioning is not precise.

It should be noted that the above examples are only used to illustrate the applicable application scenarios of the embodiments of the present application, and should not be construed as limitations on the application scenarios of the embodiments of the present application.

Therefore, in order to solve the problems existing in the prior art, the present application proposes that the time dimension is continuous, and therefore, the vehicle-mounted device, such as a lidar, can be controlled in the time dimension to continuously collect environmental information around the vehicle, and by continuously collecting The environmental information around the vehicle locates the current position of the vehicle. Because the environmental information around the vehicle is continuously collected in the time dimension in this application, and the time dimension is not affected by conditions such as road congestion. Therefore, after the vehicle is started, the collected environmental information around the vehicle can be updated in time, thereby improving the accuracy of positioning.

It should be understood that, in practical applications, the technical solutions of the present application can be applied not only to vehicle positioning, but also to aircraft positioning, for example, in a drone positioning scenario, to improve positioning accuracy. Wherein, the present application takes vehicle positioning as an example for description, however, this should not be construed as a limitation on the application scope of the present application.

The technical solutions of the present application and how the technical solutions of the present application solve the above-mentioned technical problems will be described in detail below with specific examples. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

FIG. 2 is a flowchart of a positioning method provided by an embodiment of the present application. The execution subject of this embodiment is, for example, a vehicle, and may also be implemented by components in the vehicle, such as a processing device, circuit, chip and other components in the vehicle, or a cloud server that communicates with the vehicle through a gateway. This application does not address this. limit. As shown in FIG. 2, the method of the embodiment of the present application includes:

S201. At the current moment, acquire first sensing information through a vehicle-mounted sensing device.

The first sensing information includes the coordinates of the feature points in the vehicle body coordinate system collected by the vehicle-mounted sensing device at the current moment and the odometer information of the vehicle at the current moment.

In this step, optionally, the vehicle body coordinate system may be a plane coordinate system, such as a plane Cartesian coordinate system, a polar coordinate system, or a space coordinate system, such as a space Cartesian coordinate system, a cylindrical coordinate system, or a spherical coordinate system. There is no restriction on this. The present embodiment is described by taking a space rectangular coordinate system as an example.

Optionally, the vehicle body coordinate system is a space Cartesian coordinate system, and the origin of the vehicle body coordinate system can be located at any position on the vehicle. For example, as shown in FIG. It is the X axis, the direction perpendicular to the travel direction on the horizontal plane is the Y axis, and the direction perpendicular to the travel direction on the vertical plane is the Z axis.

It should be noted that the origin of the vehicle body coordinate system is determined with the vehicle as the reference object, but the position of the vehicle changes during the driving process of the vehicle. Therefore, the origin of the vehicle body coordinate system corresponding to different positions of the vehicle is different. .

After the vehicle is started, the environmental information around the vehicle and the odometer information of the vehicle are obtained through the vehicle-mounted sensing device. Wherein, the vehicle-mounted sensing device is, for example, a multi-sensor integrated system, which may include, for example, a lidar and an inertial detection unit. The lidar is used to scan the surrounding environment of the vehicle to obtain environmental information around the vehicle, and the inertial detection unit is used to scan the surrounding environment of the vehicle. Get the odometer information of the vehicle.

It should be noted that, in some possible designs, the point cloud of environmental information around the vehicle may also be obtained through other sensors, for example, ultrasonic sensors.

At the current moment, the lidar in the vehicle-mounted sensing device emits laser light to obtain the point cloud corresponding to the surrounding environment of the vehicle, and the inertial detection unit obtains the odometer information at the current moment, so that the vehicle can pass the point cloud corresponding to the surrounding environment of the vehicle at the current moment. And the odometer information obtains the sensing information at the current moment, that is, the first sensing information. The odometer information may include, for example, steering information of the vehicle after starting, the number of turns of the wheels, and the like.

Optionally, when the vehicle-mounted sensing device acquires the point cloud and odometer information corresponding to the surrounding environment of the vehicle at the current moment, it can directly send the acquired point cloud and odometer information corresponding to the surrounding environment of the vehicle to the vehicle processing device, where The vehicle processing device processes the point cloud and odometer information corresponding to the surrounding environment of the vehicle to obtain the first sensing information. For example, the vehicle processing device extracts at least one feature point from the point cloud corresponding to the surrounding environment of the vehicle, maps the coordinates of the feature point in the coordinate system of the vehicle-mounted sensing device to the vehicle body coordinate system, and determines that the at least one feature point is located in the vehicle body. The coordinates in the coordinate system.

Or, the vehicle-mounted sensing device performs preliminary processing on the acquired point cloud and odometer information corresponding to the surrounding environment of the vehicle, for example, data format conversion, extraction of feature points in the point cloud, etc. The point cloud and the inertial detection unit acquire the odometer information at the current moment and send it to the processing device of the vehicle. The vehicle processing device acquires the first sensing information according to the preliminarily processed point cloud corresponding to the surrounding environment of the vehicle and the inertial detection unit.

Still alternatively, the vehicle-mounted sensing device obtains the first sensing information according to the obtained point cloud and odometer information corresponding to the surrounding environment of the vehicle at the current moment, and then sends the first sensing information to the processing device of the vehicle. In this way, when the vehicle is positioned, the vehicle processing device can directly use the first sensing information, thereby reducing the processing amount of the vehicle processing device and accelerating the positioning speed of the vehicle processing device.

S202: Acquire second sensing information obtained by the vehicle-mounted sensing device at a critical moment.

The second sensing information includes the coordinates of the feature points in the vehicle body coordinate system collected by the vehicle-mounted sensing device at the critical moment and the odometer information of the vehicle at the critical moment.

The critical moment includes a first critical moment, the first critical moment is the moment at which the second sensing information is acquired according to the time interval, and the time interval between the critical moment and the current moment is less than or equal to a preset duration.

In this step, because in the prior art, by setting a preset distance, every time the vehicle travels a preset distance, the on-board sensing device collects environmental information and odometer information around the vehicle, so that the vehicle processing device obtains the sensing information , according to the sensing information obtained many times, but the road congestion makes the vehicle travel slowly, and the sensing information is updated slowly. In addition, due to road congestion, the environmental information around the vehicle is blocked by obstacles such as surrounding vehicles, which will itself cause a small sensing range. Moreover, in a congested road section, sensing information is obtained according to the preset distance. The sensing information is only obtained once when the preset distance is traveled, resulting in less effective information in the sensing information, which affects the accuracy of positioning. The effective information is the information in the perception information that can improve the positioning accuracy.

Therefore, in this application, after the vehicle is started, the on-board sensing device is made to continuously obtain the point cloud and odometer information corresponding to the surrounding environment of the vehicle in the time dimension. For example, the collection time period is preset, and when the collection time period arrives , the vehicle-mounted sensing device obtains the point cloud and odometer information corresponding to the surrounding environment of the vehicle once. Or, according to the driving speed of the vehicle, adjust the time interval for obtaining the point cloud and odometer information corresponding to the surrounding environment of the vehicle twice by the vehicle-mounted sensing device. Correspondingly, corresponding to each time the vehicle-mounted sensing device obtains the corresponding point cloud and odometer information of the surrounding environment of the vehicle, the vehicle processing device obtains the sensing information once.

At the current moment, the vehicle processing apparatus acquires sensing information corresponding to at least one critical moment, that is, the second sensing information. The critical moment here is the moment at which the second sensing information is acquired according to the time interval. The time interval between each critical moment and the current moment is less than or equal to the preset duration.

For example, if the preset duration is 5 minutes, the moment before the current moment and within 5 minutes interval from the current moment when the sensor device collects the environmental information and odometer information around the vehicle is the critical moment. As shown in FIG. 4 , after the vehicle is started, the sensing device collects environmental information and odometer information around the vehicle every 30S, so that the vehicle obtains sensing information every 30S. If the current time is 10:00, the sensing information obtained after 9:55 and before 10:00 is the sensing information corresponding to the critical time. Among them, the vehicle arrives at position 1 in Figure 4 at 9:55, and the time when the vehicle arrives at position 2 in Figure 4 is one of the key moments from the last time the sensor device collected the environmental information and odometer information around the vehicle. The time interval between them is 30s. At position 2 in Figure 4, the sensing device collects environmental information and odometer information around the vehicle, and the vehicle obtains sensing information. Therefore, when the vehicle arrives at position 3 in Fig. 4 at 10:00, the critical moment after 9:55 and before 10:00 is the moment marked "☆" in Fig. 4 .

Optionally, after the vehicle processing device obtains the sensing information each time, the sensing information is saved, and when the second sensing information is obtained at the current time, the vehicle may be collected according to the current time and the sensing device corresponding to the stored sensing information. At the time of the surrounding environment information and odometer information, the second sensing information is obtained from the stored sensing information.

Optionally, when acquiring the second sensing information at the current moment, the second sensing information corresponding to each critical moment may be acquired from the list of critical moments. For example, after each acquisition of sensing information by the vehicle processing device, the sensing information is saved, and according to the critical moment corresponding to the sensing information and the critical moment corresponding to each stored sensing information, the information related to the sensor in the key list is deleted. The time interval between the critical moments corresponding to the sensing information is greater than the sensing information of the preset duration, and the list of critical moments is updated.

Optionally, the critical moment further includes a second critical moment, where the second critical moment is the moment at which the second sensing information is obtained according to the distance interval, wherein the driving distance of the vehicle from the position at the second critical moment to the position corresponding to the current moment Less than or equal to the preset distance.

After the vehicle is started, the on-board sensing device can continuously obtain the corresponding point cloud and odometer information of the surrounding environment of the vehicle according to the distance interval. For example, the distance interval for collection is preset as 100 meters, and the vehicle-mounted sensing device obtains the point cloud and odometer information corresponding to the surrounding environment of the vehicle once every 100 meters of vehicle travel. Correspondingly, corresponding to each time the vehicle-mounted sensing device obtains the point cloud and odometer information corresponding to the surrounding environment of the vehicle, the vehicle processing device obtains the sensing information once.

In this way, at the current moment, the vehicle processing device obtains the second sensing information corresponding to at least one second critical moment. For example, as shown in FIG. 5 , after the vehicle is started, the vehicle processing device obtains the sensing information every 100 meters that the vehicle travels. , the positions of the vehicle when the vehicle-mounted sensing device obtains the point cloud and odometer information corresponding to the surrounding environment of the vehicle respectively correspond to S1-S7 in the figure. The preset distance is 500 meters, when the vehicle travels 50 meters from S7 to S8 in Figure 5, the vehicle is positioned, and the vehicle is located at S8 in Figure 5 at the current moment, then S3-S7 in Figure 5 corresponds to the second key time.

After the vehicle is started, the on-board sensor device can continuously obtain the corresponding point cloud and odometer information of the surrounding environment of the vehicle according to the time interval and distance interval. For example, on the basis of Figure 4 and Figure 5, the on-board sensor collects the surrounding environment of the vehicle every 30s. In this way, the vehicle obtains sensing information every 30s, and the preset duration is 5 minutes. In addition, every 100 meters the vehicle travels, the on-board sensor collects environmental information and odometer information around the vehicle, so that the vehicle obtains sensing information every 100 meters, and the preset distance is 500 meters. As shown in Figure 6, "○" indicates the time when the point cloud and odometer information corresponding to the surrounding environment of the vehicle are obtained according to the time interval, and "●" is the time when the point cloud and odometer information corresponding to the surrounding environment of the vehicle is obtained according to the distance interval.

Optionally, in practical application, the time when the vehicle-mounted sensing device obtains the corresponding point cloud and odometer information of the surrounding environment of the vehicle according to the time interval and the time when the vehicle-mounted sensor device obtains the corresponding point cloud and odometer information of the surrounding environment of the vehicle according to the distance interval. It may be the same time. In Figure 6, "□" indicates the time when the vehicle-mounted sensing device continuously obtains the corresponding point cloud and odometer information of the surrounding environment of the vehicle according to the time interval and the distance interval.

Corresponding to Fig. 6, when the vehicle drives to position 1 in Fig. 6 (ie, position 1 in Fig. 4) at 9:55:00, and at position 2 in Fig. 6 (ie, position 2 in Fig. 4), the sensing device Collect the environmental information and odometer information around the vehicle, when the vehicle travels to S8 (ie, position 3 in Figure 4) at 10:55:00, at the current moment, the corresponding moments of the first critical moment and the second critical moment are as follows: As shown in FIG. 6 , the critical moment is the union of the first critical moment and the second critical moment.

It should be noted that the critical moment mentioned below may be the first critical moment, or the second critical moment, or a combination of the first critical moment and the second critical moment.

S203: Determine the position of the vehicle at the current moment according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information.

In this step, after acquiring the first sensing information and the at least one second sensing information, according to the first sensing information and the at least one second sensing information, the sign information of the surrounding environment of the vehicle at the current setting time is obtained, and the The sign information is compared with the map information of the driving area of the vehicle to obtain the current position of the vehicle.

Optionally, the map information of the driving area of the vehicle is the map information obtained according to the position during the previous positioning. For example, the map information of the driving area of the vehicle is the map information obtained according to the position of the last positioning.

When the vehicle is started, the position of the vehicle is initialized, for example, the initial position of the vehicle is positioned through GPS, or the initial position of the vehicle is input. After the position of the vehicle is initialized, the map information of the area where the current vehicle is currently located is acquired according to the initial position of the vehicle.

After the vehicle is started, the location of the vehicle changes, and the map of the area where it is located will also change. Therefore, after locating the vehicle, the map information needs to be updated according to the location of the vehicle. In this way, compared with the map information before the update , the updated map information has a high degree of matching with the area where the vehicle is located. Therefore, in the next positioning, the position of the vehicle positioning can be more accurate according to the updated map information.

Optionally, in S203, the pose of the vehicle at the current moment is determined according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information.

Specifically, for the same target, the different postures of the vehicle at the same position, for example, the orientation of the vehicle is different, and the coordinate system of the vehicle body is different. When shooting at the target, since the position of the target in space is fixed, the coordinates of the feature points obtained by the laser beam are different in different vehicle body coordinate systems. Therefore, according to the map information of the driving area of the vehicle and the first sensing information and at least one second sensing information, not only the position of the vehicle at the current moment, but also the posture of the vehicle at the position can be determined.

For example, as shown in FIG. 7a and FIG. 7b, for the same billboard on the roadside, the information of the billboard is collected from different postures of the vehicle at the same position. When the vehicle faces the first direction and scans the billboard through the lidar, the position of the collected at least one feature point of the billboard in the first vehicle body coordinate system is shown in Figure 7a. When the vehicle faces the second direction and scans the billboard through the lidar, the position of at least one feature point of the collected billboard in the second vehicle body coordinate system is shown in Figure 7b.

When the billboards under the first vehicle body coordinate system and the billboards under the second vehicle body coordinate system are respectively matched with the billboards in the map information, the first vehicle body coordinate system and the second vehicle body coordinate system can be determined respectively. , according to the first vehicle body coordinate system and the second vehicle body coordinate system to determine the attitude of the vehicle at this position.

In this embodiment, after the vehicle is started, the sensing information of the vehicle is acquired according to the time interval, and when the vehicle is positioned, the first sensing information corresponding to the current moment and the second sensing information corresponding to at least one critical moment are acquired. The sensor information, the at least one second sensor information, and the map information locate the vehicle. Since the sensing information is obtained from the time dimension, the process of obtaining the sensing information is not affected by road congestion, so that the sensing information used for positioning can be updated according to the time interval when the vehicle is running, thereby improving the accuracy of positioning. Moreover, the sensor information is obtained from the time dimension. When the vehicle is running at a low speed, the environmental information around the vehicle can be collected in the gap between the vehicles. At this time, due to the slow speed of the vehicle, the collected environmental information around the vehicle is clearer. To further improve the accuracy of positioning.

FIG. 8 is a flowchart of a positioning method provided by another embodiment of the present application. On the basis of the embodiment shown in FIG. 2 , as shown in FIG. 8 , the method of the embodiment of the present application includes:

S801. At the current moment, obtain first sensing information through a vehicle-mounted sensing device.

In this step, for the implementation of S801, reference may be made to S201, which will not be repeated here.

S802. Acquire second sensing information obtained by the vehicle-mounted sensing device at a critical moment.

In this step, for the implementation of S802, reference may be made to S202, which will not be repeated here.

S803. According to the odometer information in the first sensing information and the odometer information in the second sensing information, map the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment, respectively, to obtain the information collected at the critical moment The coordinates of the feature point in the vehicle body coordinate system at the current moment.

In this step, when the vehicle is powered on, the position of the vehicle when the vehicle is started is obtained and the vehicle-mounted sensing device, such as an inertial detection unit, is started. After the vehicle is started, the inertial detection unit records the odometer information during the driving of the vehicle, for example, the steering information of the vehicle after starting, the number of turns of the wheels, the speed of the vehicle, and the like.

Therefore, according to the odometer information of the vehicle, the relative position information of the position of the vehicle relative to the power-on position of the vehicle can be determined when the odometer information is recorded.

Therefore, through the odometer information at t1 and the odometer information at t2, the travel distance and the rotation angle of the vehicle from the position at t1 to the position at t2 can be determined. That is, through the odometer information at t1 and the odometer information at t2, the relative position information of the position of the vehicle at t2 relative to the position of the vehicle at t1 is determined.

Therefore, according to the odometer information in the first sensing information and the odometer information in the second sensing information, the coordinates of at least one feature point collected at the critical moment can be respectively mapped to the vehicle body coordinate system at the current moment, The coordinates of at least one feature point collected at the critical moment in the vehicle body coordinate system at the current moment are obtained.

Optionally, a specific implementation manner of S803 is:

S8031. Determine the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the critical moment according to the mileage information in the first sensing information and the mileage information in the second sensing information.

In this step, the vehicle travels from the location of the critical moment to the location of the current moment, the vehicle turns left, and the vehicle turns left from the location of the critical moment to the location of the current moment, which is recorded in the odometer information of the vehicle. Therefore, through the odometer information at the critical moment and the odometer information at the current moment, it is possible to know the turning direction of the vehicle from the position at the critical moment to the position at the current moment, and the vehicle turning left from the position at the critical moment to the position at the current moment. driving distance.

Therefore, through the odometer information at the current moment and the odometer information at the critical moment, the mapping matrix of the vehicle body coordinate system at t1 and the vehicle body coordinate system at the critical moment can be calculated. The calculation formula is for example Formula 1:

T _key ×T _key→cur =T _cur Formula 1

Among them, T _key represents the coordinate matrix of the body coordinate system of the vehicle relative to the power-on position of the vehicle at any critical moment, T _cur represents the coordinate matrix of the vehicle body coordinate system of the vehicle relative to the power-on position of the vehicle at the current moment, and T _{key →cur} represents the mapping matrix of the vehicle body coordinate system at the critical moment relative to the vehicle body coordinate system at the current moment.

Therefore, the coordinate mapping relationship between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the critical moment is determined according to the odometer information at the critical moment and the odometer information at the current moment.

S8032. According to the coordinate mapping relationship, map the coordinates of the feature points collected at the first critical moment to the vehicle body coordinate system at the current moment respectively, and obtain the coordinates of the feature points collected at the first critical moment under the vehicle body coordinate system at the current moment. .

对于其中一个关键时刻的特征点，映射到当前时刻的车体坐标系下的坐标通过公式二获得：In this step, according to formula 1, it can be known that the mapping matrix

For a feature point at one of the key moments, the coordinates mapped to the vehicle body coordinate system at the current moment are obtained by formula 2:

P _cur =T _key→cur ×P _key Formula 2

Among them, P _cur represents the coordinates of one of the feature points at the critical moment in the vehicle body coordinate system at the current moment, and P _key represents the coordinates of one of the feature points at the critical moment in the vehicle body coordinate system at the critical moment.

S804: Determine the position of the vehicle at the current moment according to the coordinates and map information of the feature points collected at each critical moment and the feature points collected at the current moment respectively in the vehicle body coordinate system at the current moment.

In this step, for the sensing information at any critical moment, the coordinates of at least one feature point collected at the critical moment are mapped to the vehicle body coordinate system at the current moment according to the corresponding mapping matrix, so that the vehicle body coordinates at the current moment are mapped according to the corresponding mapping matrix. feature points under the system (including at least one feature point collected at each critical moment mapped to the feature point obtained under the vehicle body coordinate system at the current moment and at least one feature point collected at the current moment) and map information to determine the position of the vehicle at the current moment .

Wherein, since the coordinates of at least one feature point collected at the critical moment are all mapped to the vehicle body coordinate system at the current moment according to the corresponding mapping matrix, the number of feature points at the current moment can be increased. In this way, the contour of the target object around the vehicle extracted through the feature points is clearer and closer to its real contour, so that when positioning according to the map information, the contour of the target object extracted through the feature points matches the contour of the target object in the map information. higher, thereby improving the accuracy of positioning.

FIG. 9 is a flowchart of a positioning method provided by another embodiment of the present application. On the basis of the embodiment shown in FIG. 8 , the method of the embodiment of the present application includes:

S901. At the current moment, obtain first sensing information through a vehicle-mounted sensing device.

In this step, for the implementation of S901, reference may be made to S201, which will not be repeated here.

S902. Acquire second sensing information obtained by the vehicle-mounted sensing device at a critical moment.

In this step, for the implementation of S902, reference may be made to S202, which will not be repeated here.

S903. According to the odometer information in the second sensing information and the odometer information in the second sensing information, map the coordinates of the feature points collected at the critical moment to the vehicle body coordinate system at the current moment, and obtain the data collected at the critical moment. The coordinates of the feature point in the vehicle body coordinate system at the current moment.

In this step, for the implementation of S903, reference may be made to S803, which will not be repeated here.

S904, at the current moment, for each particle in the M particles corresponding to the vehicle, according to the feature points collected at the critical moment and the feature points collected at the current moment, the coordinates of the vehicle body coordinate system at the current moment and the coordinates of each particle respectively position, to obtain the matching degree between the feature points collected at the current moment and the key moment and the target object in the map information.

Among them, the M particles are the particles used when positioning the vehicle last time, and the position of each particle is based on the odometer information when the vehicle was positioned last time, the odometer information at the current moment, and the position of each particle when the vehicle was positioned last time. The position of the particle is obtained, where M is a positive integer.

In this step, when locating the vehicle, the framework of particle filtering can be used. Specifically:

As shown in FIG. 10 , when the vehicle is just started, the initial position of the vehicle is obtained, and some particles are arranged around the vehicle, that is, initialization particles. For example, the positions of the initialization particles satisfy a normal distribution. Among them, each particle is used to simulate the vehicle, the position of the particle simulates the position of the vehicle, and the position of each particle is recorded. At this point, the position of the particle is the initialization position

After the vehicle is started, the motion process of each particle is consistent with the motion process of the vehicle. The odometer information of the vehicle can determine the motion information of the vehicle from one location to another, for example, the distance traveled by the vehicle, the direction of turning during the driving process, and the like. Therefore, the motion process of the particles can be predicted according to the odometer information of the vehicle, thereby predicting the position of the particles.

For the M particles at the current moment, the M particles are the particles used in the last vehicle positioning, according to the position of each particle in the M particles during the last vehicle positioning, and the mileage of the vehicle during the last positioning. The odometer information and the odometer information at the current moment are used to determine the position of each particle at the current moment.

At the current moment, according to the feature points under the vehicle body coordinate system at the current moment (including at least one feature point collected at each critical moment mapped to the feature point obtained under the vehicle body coordinate system at the current moment and at least one feature point collected at the current moment), The environmental information around the vehicle at the current moment can be determined, that is, the sign information around the vehicle can be extracted according to the feature points in the vehicle body coordinate system at the current moment, such as the target object to be matched around the vehicle, and the position of the target object to be matched relative to the vehicle.

Among them, the feature points under the vehicle body coordinate system at the current moment are actually the feature points collected by the laser radar at the real position of the vehicle. Therefore, the target objects to be matched around the vehicle obtained according to the feature points under the vehicle body coordinate system at the current moment, In fact, the target object to be matched is viewed from the real position of the vehicle, and the coordinates of the target object to be matched under the vehicle body coordinates are actually the relative position of the target object to be matched relative to the real position of the vehicle. Therefore, in the optimal case, the target object to be matched extracted from the feature points in the vehicle body coordinate system at the current moment completely matches the target object in the map information.

Therefore, since each particle is the real position of the simulated vehicle, and the odometer information recorded in the vehicle cannot faithfully reflect the actual motion process of the vehicle, for example, the driving distance of the vehicle obtained from the odometer information is the actual driving distance of the vehicle. There are some differences. Therefore, when the position of the particle at the current moment is determined according to the odometer information, there is a difference between the position of the particle and the real position of the vehicle.

Therefore, for each particle, according to the feature points under the vehicle body coordinate system at the current moment and the position of the particle at the current moment, the target object to be matched and the target in the map information can be extracted from the feature points under the vehicle body coordinate system at the current moment. The matching degree of the object determines the difference between the position of the particle and the real position of the vehicle.

Optionally, a specific implementation manner of S904 is:

S9041. Map the coordinates of the feature points collected at the current moment and at the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with the particle as the origin, respectively.

Specifically, each particle is selected one by one, and for each particle, the particle coordinate system with the particle as the coordinate origin replaces the vehicle body coordinate system at the current moment, and the feature points under the vehicle body coordinate system at the current moment are mapped to the particle coordinate system. , to obtain the coordinates of the feature points in the vehicle body coordinate system at the current moment mapped to the particle coordinate system.

The particle coordinate system may be a plane coordinate system, such as a plane rectangular coordinate system, a polar coordinate system, or a space coordinate system, such as a space rectangular coordinate system, a cylindrical coordinate system, or a spherical coordinate system, which is not limited in this application. In this embodiment, the space rectangular coordinate system is used as an example for description.

Optionally, the vehicle body coordinate system and the particle coordinate system may be the same type of coordinate system. For example, the vehicle body coordinate system and the particle coordinate system are both space rectangular coordinate systems, or the vehicle body coordinate system and the particle coordinate system may be different. The type of coordinate system, for example, the vehicle body coordinate system is a space rectangular coordinate system, and the particle coordinate system is a spherical coordinate system, which is not limited in this embodiment of the present application.

S9042: Obtain the matching degree between the target object to be matched and the corresponding target object in the map information, which is formed by the feature points that are mapped to the current moment in the particle coordinate system and the feature points collected at the critical moment.

Specifically, according to the current moment mapped to the particle coordinate system and the feature points collected at at least one critical moment, the target objects to be matched around the vehicle from the current moment are extracted, and the map information corresponding to the position of the particle is determined to determine the particle in the map information. The position of the particle in the map information is taken as the coordinate origin, the target object to be matched is matched with the corresponding target object in the map information, and the target object to be matched is determined according to the degree of coincidence between the target object to be matched and the corresponding target object in the map information. Matching degree with the corresponding target in the map information.

Since the motion of the particle is consistent with the motion of the vehicle, if the position of the particle is closer to the real position of the vehicle, it is mapped to the target object to be matched and the map information composed of the feature points in the vehicle body coordinate system at the current moment of the particle coordinate system. The higher the matching degree of the corresponding target.

As shown in Figure 11, the vehicle coordinate system and the particle coordinate system are the space rectangular coordinate system (the space rectangular coordinate system is not shown in Figure 11), in the map information, the real position of the vehicle is point O, and the position of one particle is is point O1. For a roadside billboard, the billboard and its position are formed according to the feature points in the vehicle body coordinate system at the current moment, as shown by the solid line in Figure 11 . Among them, the billboard shown by the solid line coincides with the billboard in the map information.

After the feature points under the vehicle body coordinate system at the current moment are mapped to the particle coordinate system, the billboard and the position formed by the feature points are shown as dotted lines in Figure 11 .

If the position of the particle is the real position of the vehicle, in FIG. 11 , the position of the billboard indicated by the solid line coincides with the position of the billboard indicated by the dotted line. The matching degree of the particles is determined according to the distance between the position of the billboard indicated by the solid line and the position of the billboard indicated by the dotted line. The smaller the distance, the higher the matching degree.

Optionally, at least one feature point collected at each critical moment is mapped to the vehicle body coordinate system at the current moment, resulting in more feature points in the vehicle body coordinate system at the current moment. In addition, when the environmental information around the vehicle is collected at different critical moments, repeated feature points will be collected, thereby increasing the amount of calculation and affecting the positioning efficiency. Therefore, before S904, also include:

S1001. Determine a target feature point according to at least one feature point collected at each critical moment and the feature value of each feature point in the feature points collected at the current moment.

In this step, from the feature points under the vehicle body coordinate system at the current moment (including at least one feature point collected at each critical moment mapped to the feature point obtained under the vehicle body coordinate system at the current moment and at least one feature point collected at the current moment) Select stable and representative target feature points from the , and save the target feature points. On the basis of reducing the number of feature points, the environment information around the vehicle extracted through the target feature points is made close to the environment information around the vehicle extracted through the feature points in the vehicle body coordinate system at the current moment.

Optionally, the feature value of each feature point in the feature points in the vehicle body coordinate system at the current moment is calculated according to the evaluation function, and one or more feature points are selected as the target feature point according to the feature value of each feature point.

Optionally, the feature value of each feature point in the feature points in the vehicle body coordinate system at the current moment is calculated according to the evaluation function, and one or more feature points with the largest feature value are selected as the target feature point according to the size of the feature value.

S1002: Determine the target feature point again according to the feature points collected at each critical moment and the feature values of each feature point except the feature points included in the feature point set among the feature points collected at the current moment.

The feature points included in the feature point set are the feature points located within the preset distance range of the last determined target feature point and the last determined target feature point.

In this step, after the target feature point is determined through S1001, since the target feature point is stable and representative, in order to reduce the number of feature points, the distance can be deleted from the feature points in the vehicle body coordinate system at the current moment. A feature point set is obtained from the feature points within the preset distance range of the target feature point and the target feature point.

Then, repeat S1001 and S1002, re-determine target feature points from the feature point set, and obtain a new feature point set according to the re-determined target feature points.

S1003. When the number of target feature points meets the preset number, obtain N target feature points, where N is equal to the preset number.

In this step, when the number of target feature points meets the preset number, the acquisition of new target feature points is stopped, and the vehicle is positioned according to the currently obtained target feature points.

S905. Obtain K particles according to the matching degree of each of the M particles at the current moment and the M particles.

Among them, K is a positive integer.

In this step, although the motion process of the particles is consistent with the motion process of the vehicle, the odometer information recorded in the vehicle cannot faithfully reflect the real motion process of the vehicle. Actual driving distances may vary. Therefore, when the position of the particle at the current moment is determined according to the odometer information, the position of the particle relative to the vehicle at the current moment is different from the position of the particle relative to the vehicle at the last positioning. Therefore, the matching degree of the particles changes as the vehicle moves. That is to say, particles with a high matching degree last time may have a lower matching degree at the current moment.

Therefore, it is necessary to resample the particles according to the matching degree of each of the M particles, that is, to re-determine the K particles used for vehicle positioning.

Optionally, the matching degree of the particle indicates the closeness of the position of the particle to the real position of the vehicle, and the higher the matching degree, the closer the position of the particle is to the real position of the vehicle. Therefore, M particles with higher particles are selected and determined as K particles. For example, a preset matching degree is set, and L particles whose matching degree is greater than or equal to the preset matching degree among the M particles are obtained, and are determined as K particles.

Optionally, after obtaining L particles whose matching degree is greater than or equal to the preset matching degree among the M particles, at least one particle may be selected from the L particles, and K is obtained according to the L particles and the selected at least one particle. particles.

Optionally, after at least one particle is selected from the L particles, the particles may be copied at least once according to the matching degree of each particle in the at least one particle, that is, the number of particles is increased. High, the more the number of particles after the increase, K particles are obtained according to the L particles and the particles obtained by the increase.

S906: Obtain the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment.

In this step, since the position of each particle simulates the real position of the vehicle, at the current moment, the position of the vehicle at the current moment can be determined according to the positions of the K particles.

Optionally, according to the positions of the K particles, the average position of the K particles is obtained, and the average position of the K particles is determined as the position of the vehicle at the current moment.

Optionally, according to the position of the K particles and the matching degree of each particle, the weighted average position of the K particles is obtained, and the weighted average position of the K particles is determined as the position of the vehicle at the current moment.

When the vehicle is positioned next time, the K particles determined at the current moment replace the M particles in S1004, and the above steps are repeated to position the vehicle.

Optionally, according to the positions of the K particles, the obtained position of the vehicle at the current moment is not the real position of the vehicle at the current moment. Therefore, if there is a large difference between the obtained position of the vehicle at the current moment and the real position of the vehicle at the current moment according to the positions of the K particles, there will be potential safety hazards. Therefore, the method of the embodiment of the present application also includes:

S907: Obtain an evaluation value of the position of the vehicle at the current moment according to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment.

The evaluation value represents the difference between the position of the vehicle at the current moment and the real position information of the vehicle at the current moment.

In this step, the distribution variance of the K particles is calculated according to the position of each particle in the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, and the evaluation value of the position of the vehicle at the current moment is obtained according to the distribution variance. For example, the distribution variance is determined as an evaluation value of the position of the vehicle at the current time. The greater the distribution variance, the greater the difference between the vehicle's position at the current moment and the vehicle's true position. Therefore, according to the evaluation value, it can be determined, for example, whether to remotely control the vehicle, or activate other positioning devices to locate the vehicle.

FIG. 12 is a schematic structural diagram of a positioning device according to an embodiment of the present application. As shown in FIG. 12 , the positioning device may be the vehicle as described above, or may be a component of the vehicle (eg, an integrated circuit, a chip, etc.). The positioning device may also be a server, such as a cloud server, or a component of the server (eg, an integrated circuit, a chip, etc.). The positioning device may also be other communication modules, which are used to implement the methods in the method embodiments of the present application and the above-mentioned optional embodiments. The positioning apparatus may include: an acquisition module 1201 and a positioning module 1202 .

The acquisition module 1201 is used to execute:

Any optional embodiment of S201, S202, and S201, S202 in the embodiment shown in FIG. 2, and any optional embodiment of S801, S802, and S801, S802 in the embodiment shown in FIG. 8, For details, refer to the detailed description in the method example, which is not repeated here.

A positioning module 1202 for executing:

S203 in the embodiment shown in FIG. 2 and any optional embodiments thereof, S803, S804, and any optional embodiments of S803 and S804 in the embodiment shown in FIG. 8, and the embodiment shown in FIG. 9 Any optional embodiment of S903-S907 and S903-S907 in . For details, refer to the detailed description in the method example, which is not repeated here.

The acquisition module 1201 is configured to acquire first sensing information through the vehicle-mounted sensing device at the current moment, wherein the first sensing information includes the feature points collected by the vehicle-mounted sensing device at the current moment in the vehicle body coordinate system and the odometer information of the vehicle at the current moment.

The acquisition module 1201 is further configured to acquire the second sensing information obtained by the vehicle-mounted sensing device at the critical moment, wherein the second sensing information includes the feature points collected by the vehicle-mounted sensing device at the critical moment in the vehicle body coordinate system. Coordinates and odometer information of the vehicle at that critical moment. The critical moment includes a first critical moment, the first critical moment is the moment at which the second sensing information is obtained according to the time interval, and the time interval between the first critical moment and the current moment is less than or equal to a preset duration.

The positioning module 1202 is configured to determine the position of the vehicle at the current moment according to the map information of the driving area of the vehicle and the first sensing information and the second sensing information.

It should be understood that the positioning device in this embodiment of the present application may be implemented by software, for example, a computer program or instruction having the above-mentioned functions, and the corresponding computer program or instruction may be stored in a memory inside the terminal, and read by a processor. Corresponding computer programs or instructions inside the memory implement the above functions.

Alternatively, the positioning device in the embodiment of the present application may also be implemented by hardware. The acquiring module 1201 and the positioning module 1202 are processors (such as NPU, GPU, and processors in a system chip).

Alternatively, the positioning apparatus in this embodiment of the present application may also be implemented by a combination of a processor and a software module.

Optionally, the positioning module 1202 is further configured to map the coordinates of the feature points collected at the critical moment to the vehicle body at the current moment according to the odometer information in the first sensing information and the odometer information in the second sensing information. In the coordinate system, the coordinates of the feature points collected at the critical moment in the vehicle body coordinate system at the current moment are obtained.

The position of the vehicle at the current moment is determined according to the coordinates and map information of the feature points collected at the critical moment and the feature points collected at the current moment respectively in the vehicle body coordinate system at the current moment.

Optionally, the positioning module 1202 is further configured to, at the current moment, for each particle in the M particles corresponding to the vehicle, according to the feature points collected at the critical moment and the feature points collected at the current moment, respectively, the vehicle body coordinates at the current moment. The coordinates under the system and the position of each particle are obtained to obtain the matching degree between the feature points collected at the current moment and the key moment and the target object in the map information, wherein the above M particles are the particles used in the last vehicle positioning, and each The position of the particle is obtained according to the odometer information when the vehicle was positioned last time, the odometer information at the current moment, and the position of each particle when the vehicle was positioned last time, and M is a positive integer;

According to the matching degree of each of the M particles at the current moment and the M particles, K particles are obtained, where K is a positive integer;

According to the positions of the K particles corresponding to the vehicle at the current moment, the position of the vehicle at the current moment is obtained.

Optionally, the positioning module 1202 is further configured to map the coordinates of the feature points collected at the current moment and the critical moment in the vehicle body coordinate system at the current moment to the particle coordinate system with each particle as the origin;

The matching degree of the target object to be matched composed of the feature points collected at the current moment and the key moment mapped to each particle coordinate system and the corresponding target object in the map information is obtained.

Optionally, the positioning module 1202 is further configured to acquire L particles whose matching degree is greater than or equal to a preset matching degree among the M particles, wherein L is less than or equal to M and less than or equal to K;

Determine L particles as K particles; or,

Get at least one particle from L particles;

From L particles and at least one particle, K particles are obtained.

Optionally, the positioning module 1202 is further configured to copy each particle at least once according to the matching degree of each particle in the at least one particle;

The L particles and the particles obtained after replication are determined as K particles.

Optionally, the positioning module 1202 is further configured to obtain the average position of the K particles according to the position of each particle in the K particles, and determine the average position of the K particles as the position of the vehicle at the current moment.

Optionally, the positioning module 1202 is further configured to obtain an evaluation value of the position of the vehicle at the current moment according to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment. Wherein, the evaluation value indicates the difference between the position of the vehicle at the current moment and the real position information of the vehicle at the current moment.

Optionally, the positioning module 1202 is further configured to determine the vehicle body coordinate system corresponding to the current moment and the vehicle body corresponding to the first critical moment according to the mileage information in the first sensing information and the mileage information in the second sensing information The coordinate mapping relationship of the coordinate system;

According to the coordinate mapping relationship, the coordinates of the feature points collected at the first critical moment are respectively mapped to the vehicle body coordinate system at the current moment, and the coordinates of the feature points collected at the first critical moment under the vehicle body coordinate system at the current moment are obtained.

Optionally, the critical moment further includes a second critical moment, where the second critical moment is the moment at which the second sensing information is obtained according to the distance interval, wherein the driving distance of the vehicle from the position at the second critical moment to the position corresponding to the current moment Less than or equal to the preset distance.

Optionally, the positioning module 1202 is further configured to determine the pose of the vehicle at the current moment according to the map information and the first sensing information and the second sensing information.

Optionally, the positioning module 1202 is further configured to determine the target feature point according to the feature points collected at each critical moment and the feature value of each feature point in the feature points collected at the current moment;

According to the feature points collected at each critical moment and the feature values of the feature points collected at the current moment except the feature points included in the feature point set, the target feature point is determined again, and the feature points included in the feature point set are: The feature points located within the preset distance range of the last determined target feature point and the last determined target feature point;

When the number of target feature points meets the preset number, N target feature points are obtained, where N is equal to the preset number;

Correspondingly, the positioning module 1202 is also used to obtain the feature points collected at the current moment and the key moment and the map information of the target area according to the coordinates of the N target feature points in the vehicle body coordinate system at the current moment and the position of each particle. the matching degree of the target.

Optionally, the eigenvalues of the feature points are obtained through an evaluation function, and the eigenvalues are used to evaluate the stability of the feature points.

Optionally, the target feature point is the feature point with the largest feature value among the feature points.

Optionally, the origin of the vehicle body coordinate system is located at any position on the vehicle.

The apparatus of this embodiment can be used to execute the technical solutions in the foregoing method embodiments, and the implementation principles and technical effects thereof are similar, and are not repeated here.

FIG. 13 is a schematic structural diagram of a positioning device according to an embodiment of the present application. The positioning device in this embodiment may be the above vehicle, or may be a server. The positioning device can be used to implement the methods described in the foregoing method embodiments. For details, reference may be made to the descriptions in the foregoing method embodiments.

The positioning apparatus may include one or more processors 1301, and the processors 1301 may also be referred to as processing units, which may implement certain control functions. The processor 1301 may be a general-purpose processor or a special-purpose processor or the like.

Optionally, the processor 1301 may also store instructions and/or data 1303, and the instructions and/or data 1303 may be executed by the processor, so that the positioning apparatus executes the methods described in the foregoing method embodiments.

Optionally, the positioning apparatus may include one or more memories 1302, and instructions 1304 may be stored thereon, and the instructions may be executed on the processor, so that the positioning apparatus executes the above method embodiments method described. Optionally, data may also be stored in the memory. Optionally, instructions and/or data may also be stored in the processor. The processor and the memory can be provided separately or integrated together. For example, the corresponding relationship described in the above method embodiments may be stored in a memory or in a processor.

The processors and transceivers described in this embodiment can be fabricated using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), nMetal-oxide-semiconductor (NMOS) ), P-type metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (Bipolar Junction Transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc. .

It should be understood that the processor in this embodiment of the present application may be an integrated circuit chip, which has a signal processing capability. In the implementation process, each step of the above method embodiments may be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software. The above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable Logic devices, discrete gate or transistor logic devices, discrete hardware components.

It can be understood that the memory in this embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory. Volatile memory may be random access memory (RAM), which acts as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM) And direct memory bus random access memory (directrambus RAM, DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but not be limited to, these and any other suitable types of memory.

The scope of the positioning device described in the embodiments of the present application is not limited thereto, and the structure of the positioning device may not be limited by FIG. 13 . The positioning apparatus described in the embodiments of the present application may be an independent device or may be a part of a larger device.

FIG. 14 is a schematic structural diagram of a positioning system according to an embodiment of the present application. As shown in FIG. 14 , the positioning system includes: a vehicle 1401 and a vehicle-mounted sensing device 1402 .

The in-vehicle sensor device 1402 is installed on the vehicle 1401 and communicates with the vehicle 1401 .

Optionally, the in-vehicle sensing device 1402 is configured to collect environmental information and odometer information around the vehicle 1401 , and send the environmental information and odometer information around the vehicle 1401 to the vehicle 1401 .

The vehicle 1401 is used to execute the method described in the above method embodiments.

Optionally, the in-vehicle sensing device 1402 is used to collect environmental information and odometer information around the vehicle 1401, send the environmental information and odometer information around the vehicle 1401 to the vehicle 1401, and execute the methods described in the above method embodiments. method to locate the vehicle 1401.

The system in this embodiment can be used to execute the technical solutions in any of the above method embodiments, and the implementation principles and technical effects thereof are similar, and details are not described herein again.

The present application also provides a computer-readable medium on which a computer program is stored, and when the computer program is executed by a computer, implements the method shown in any of the above method embodiments.

The present application also provides a computer program product, which implements the method shown in any of the above method embodiments when the computer program product is executed by a computer.

When the above-described embodiments are implemented using software, they may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general purpose computer, special purpose computer, computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server, or data center Transmission to another website site, computer, server, or data center by wire (eg, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes an integration of one or more available media. The available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, high-density digital video discs (DVDs)), or semiconductor media (eg, solid state disks, SSD)) etc.

Claims (33)

1. A method of positioning, comprising:

at the current moment, acquiring first sensing information through a vehicle-mounted sensing device, wherein the first sensing information comprises coordinates of characteristic points acquired by the vehicle-mounted sensing device at the current moment under a vehicle body coordinate system and odometer information of a vehicle at the current moment;

acquiring second sensing information acquired through the vehicle-mounted sensing device at a key moment, wherein the second sensing information comprises coordinates of characteristic points acquired by the vehicle-mounted sensing device at the key moment under a vehicle body coordinate system and odometer information of the vehicle at the key moment, the key moment comprises a first key moment, the first key moment is a moment of acquiring second sensing information according to a time interval, and the time interval between the first key moment and the current moment is less than or equal to a preset time length;

and determining the position of the vehicle at the current moment according to the map information of the driving area of the vehicle, the first sensing information and the second sensing information.

2. The method of claim 1, wherein determining the position of the vehicle at the current time based on the map information of the vehicle travel area and the first and second sensory information comprises:

mapping the coordinates of the feature points acquired at the key moment to the vehicle body coordinate system at the current moment according to the odometer information in the first sensing information and the odometer information in the second sensing information, and acquiring the coordinates of the feature points acquired at the key moment in the vehicle body coordinate system at the current moment;

and determining the position of the vehicle at the current moment according to the coordinates of the feature points acquired at the key moment and the feature points acquired at the current moment under the vehicle body coordinate system at the current moment and the map information.

3. The method according to claim 2, wherein the determining the position of the vehicle at the current time according to the coordinates of the feature points acquired at the critical time and the feature points acquired at the current time under the vehicle body coordinate system at the current time and the map information respectively comprises:

at the current moment, for each particle in M particles corresponding to the vehicle, obtaining matching degrees of the feature points acquired at the current moment and the key moment and a target object in the map information according to coordinates of the feature points acquired at the key moment and the feature points acquired at the current moment under a vehicle body coordinate system at the current moment and the position of each particle, respectively, wherein the M particles are particles adopted when the vehicle is positioned last time, the position of each particle is obtained according to odometer information when the vehicle is positioned last time, the odometer information at the current moment and the position of each particle when the vehicle is positioned last time, and M is a positive integer;

obtaining K particles according to the matching degree of each particle in the M particles at the current moment and the M particles, wherein K is a positive integer;

and obtaining the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment.

4. The method according to claim 3, wherein the obtaining of the matching degree between the feature points acquired at the current time and the target object in the map information according to the coordinates of the feature points acquired at the key time and the feature points acquired at the current time under the vehicle coordinate system at the current time and the position of each particle respectively comprises:

respectively mapping the coordinates of the feature points acquired at the current moment and the key moment under the vehicle body coordinate system at the current moment to a particle coordinate system with the particles as the origin;

and obtaining the matching degree of a target object to be matched, which is formed by the characteristic points acquired at the current moment and the key moment and mapped to the particle coordinate system, and the corresponding target object in the map information.

5. The method according to claim 3, wherein obtaining K particles according to the matching degree of each of the M particles at the current time and the M particles comprises:

obtaining L particles with a matching degree greater than or equal to a preset matching degree in the M particles, wherein L is less than or equal to M and less than or equal to K;

determining the L particles as the K particles; or,

obtaining at least one particle from the L particles;

obtaining the K particles according to the L particles and the at least one particle.

6. The method of claim 5, wherein obtaining the K particles from the L particles and the at least one particle comprises:

according to the matching degree of each particle in the at least one particle, copying each particle at least once;

and determining the L particles and the particles obtained after copying as the K particles.

7. The method according to any one of claims 3-6, wherein the obtaining the position of the vehicle at the current time according to the positions of the K particles corresponding to the vehicle at the current time comprises:

and acquiring the average position of the K particles according to the position of each particle in the K particles, and determining the average position of the K particles as the position of the vehicle at the current moment.

8. The method according to any one of claims 3-7, further comprising:

obtaining an evaluation value of the position of the vehicle at the current moment according to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, wherein the evaluation value indicates a difference between the position of the vehicle at the current moment and real position information of the vehicle at the current moment.

9. The method according to any one of claims 2 to 8, wherein the obtaining coordinates of the feature points acquired at the key time in the vehicle body coordinate system at the current time by mapping the coordinates of the feature points acquired at the key time to the vehicle body coordinate system at the current time according to the odometer information in the second sensing information and the odometer information in the second sensing information comprises:

determining a coordinate mapping relation between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first key moment according to the mileage information in the first sensing information and the mileage information in the second sensing information;

and according to the coordinate mapping relation, respectively mapping the coordinates of the characteristic points acquired at the first key moment to the vehicle body coordinate system at the current moment, and acquiring the coordinates of the characteristic points acquired at the first key moment in the vehicle body coordinate system at the current moment.

10. The method according to any one of claims 1 to 9, wherein the critical time further includes a second critical time, the second critical time is a time when second sensing information is acquired according to a distance interval, and a travel distance from a position of the second critical time to a position corresponding to the current time is less than or equal to a preset distance.

11. The method according to any one of claims 1 to 10, wherein the determining the position of the vehicle at the current time based on the map information of the vehicle travel area and the first and second sensing information comprises:

and determining the pose of the vehicle at the current moment according to the map information and the first and second sensing information.

12. The method according to claim 3, wherein before obtaining the matching degree between the feature points acquired at the current time and the target object in the map information according to the coordinates of the feature points acquired at the key time and the feature points acquired at the current time under the vehicle coordinate system at the current time and the position of each particle, the method further comprises:

determining target feature points according to the feature points acquired at each key moment and the feature values of each feature point in the feature points acquired at the current moment;

determining target feature points again according to feature points acquired at each key moment and feature values of the feature points acquired at the current moment except feature points contained in a feature point set, wherein the feature points contained in the feature point set are feature points located in a preset distance range of the last determined target feature point and the last determined target feature point;

when the number of the target characteristic points meets a preset number, N target characteristic points are obtained, wherein N is equal to the preset number;

the obtaining of the matching degree between the feature points acquired at the current moment and the key moment and the target object in the map information according to the coordinates of the feature points acquired at the key moment and the feature points acquired at the current moment under the vehicle body coordinate system at the current moment and the position of each particle respectively includes:

and according to the coordinates of the N target characteristic points in the vehicle body coordinate system at the current moment and the position of each particle, obtaining the matching degree of the characteristic points acquired at the current moment and the key moment and the target object in the map information of the target area.

13. The method according to claim 12, wherein the feature value of the feature point is obtained by an evaluation function, and the feature value is used to evaluate the stability of the feature point.

14. The method according to claim 12 or 13, wherein the target feature point is a feature point having a largest feature value among the feature points.

15. The method according to any of claims 1-14, wherein the origin of the body coordinate system is located at any position on the vehicle.

16. A positioning device, comprising:

the acquisition module is used for acquiring first sensing information through the vehicle-mounted sensing device at the current moment, wherein the first sensing information comprises coordinates of characteristic points acquired by the vehicle-mounted sensing device at the current moment under a vehicle body coordinate system and odometer information of a vehicle at the current moment;

the acquisition module is further configured to acquire second sensing information acquired by the vehicle-mounted sensing device at a key moment, where the second sensing information includes coordinates of feature points acquired by the vehicle-mounted sensing device at the key moment in a vehicle body coordinate system and odometer information of the vehicle at the key moment, the key moment includes a first key moment, the first key moment is a moment at which second sensing information is acquired according to a time interval, and a time interval between the first key moment and the current moment is less than or equal to a preset duration;

and the positioning module is used for determining the position of the vehicle at the current moment according to the map information of the driving area of the vehicle, the first sensing information and the second sensing information.

17. The apparatus according to claim 16, wherein the positioning module, when determining the position of the vehicle at the current time according to the map information of the driving area of the vehicle and the first and second sensing information, is specifically configured to:

mapping the coordinates of the feature points acquired at the key moment to the vehicle body coordinate system at the current moment according to the odometer information in the first sensing information and the odometer information in the second sensing information, and acquiring the coordinates of the feature points acquired at the key moment in the vehicle body coordinate system at the current moment;

and determining the position of the vehicle at the current moment according to the coordinates of the feature points acquired at the key moment and the feature points acquired at the current moment under the vehicle body coordinate system at the current moment and the map information.

18. The apparatus according to claim 17, wherein the positioning module, when determining the position of the vehicle at the current time according to the coordinates of the feature points acquired at the key time and the feature points acquired at the current time in the body coordinate system at the current time and the map information, is specifically configured to:

at the current moment, for each particle in M particles corresponding to the vehicle, obtaining matching degrees of the feature points acquired at the current moment and the key moment and a target object in the map information according to coordinates of the feature points acquired at the key moment and the feature points acquired at the current moment under a vehicle body coordinate system at the current moment and the position of each particle, respectively, wherein the M particles are particles adopted when the vehicle is positioned last time, the position of each particle is obtained according to odometer information when the vehicle is positioned last time, the odometer information at the current moment and the position of each particle when the vehicle is positioned last time, and M is a positive integer;

obtaining K particles according to the matching degree of each particle in the M particles at the current moment and the M particles, wherein K is a positive integer;

and obtaining the position of the vehicle at the current moment according to the positions of the K particles corresponding to the vehicle at the current moment.

19. The apparatus according to claim 18, wherein the positioning module, when obtaining the matching degrees between the feature points acquired at the current time and the key time and the target object in the map information according to the coordinates of the feature points acquired at the key time and the feature points acquired at the current time in the vehicle coordinate system at the current time and the position of each particle, is specifically configured to:

respectively mapping the coordinates of the feature points acquired at the current moment and the key moment under the vehicle body coordinate system at the current moment to a particle coordinate system with the particles as the origin;

and obtaining the matching degree of a target object to be matched, which is formed by the characteristic points acquired at the current moment and the key moment and mapped to the particle coordinate system, and the corresponding target object in the map information.

20. The apparatus according to claim 18, wherein the positioning module is specifically configured to, when obtaining K particles according to the matching degree of each of the M particles at the current time and the M particles:

obtaining L particles with a matching degree greater than or equal to a preset matching degree in the M particles, wherein L is less than or equal to M and less than or equal to K;

determining the L particles as the K particles; or,

obtaining at least one particle from the L particles;

obtaining the K particles according to the L particles and the at least one particle.

21. The apparatus according to claim 20, wherein the positioning module, when obtaining the K particles according to the L particles and the at least one particle, is specifically configured to:

according to the matching degree of each particle in the at least one particle, copying each particle at least once;

and determining the L particles and the particles obtained after copying as the K particles.

22. The apparatus according to any one of claims 18 to 21, wherein when the location of the vehicle at the current time is obtained according to the locations of the K particles corresponding to the vehicle at the current time by the location module, the apparatus is specifically configured to:

and acquiring the average position of the K particles according to the position of each particle in the K particles, and determining the average position of the K particles as the position of the vehicle at the current moment.

23. The apparatus of any one of claims 18-22, wherein the positioning module is further configured to:

obtaining an evaluation value of the position of the vehicle at the current moment according to the position of each of the K particles corresponding to the vehicle at the current moment and the position of the vehicle at the current moment, wherein the evaluation value indicates a difference between the position of the vehicle at the current moment and real position information of the vehicle at the current moment.

24. The apparatus according to any one of claims 17 to 23, wherein the positioning module is configured to map, according to the odometer information in the second sensing information and the odometer information in the second sensing information, the coordinates of the feature point acquired at the key time to the coordinates of the vehicle body at the current time, and when obtaining the coordinates of the feature point acquired at the key time in the vehicle body coordinate system at the current time, specifically:

determining a coordinate mapping relation between the vehicle body coordinate system corresponding to the current moment and the vehicle body coordinate system corresponding to the first key moment according to the mileage information in the first sensing information and the mileage information in the second sensing information;

and according to the coordinate mapping relation, respectively mapping the coordinates of the characteristic points acquired at the first key moment to the vehicle body coordinate system at the current moment, and acquiring the coordinates of the characteristic points acquired at the first key moment in the vehicle body coordinate system at the current moment.

25. The apparatus according to any one of claims 16 to 24, wherein the critical time further includes a second critical time, the second critical time being a time at which second sensing information is acquired according to a distance interval, wherein a travel distance of the vehicle from a position of the second critical time to a position corresponding to the current time is less than or equal to a preset distance.

26. The apparatus according to any one of claims 16 to 25, wherein the positioning module is configured to, when determining the position of the vehicle at the current time according to the map information of the driving area of the vehicle and the first and second sensing information, specifically:

and determining the pose of the vehicle at the current moment according to the map information and the first and second sensing information.

27. The apparatus according to claim 18, wherein the positioning module is further configured to, before obtaining matching degrees between feature points acquired at a current time and the key time and the target object in the map information according to coordinates of the feature points acquired at the key time and the feature points acquired at the current time in the vehicle coordinate system at the current time and the position of each particle, respectively:

determining target feature points according to the feature points acquired at each key moment and the feature values of each feature point in the feature points acquired at the current moment;

determining target feature points again according to feature points acquired at each key moment and feature values of the feature points acquired at the current moment except feature points contained in a feature point set, wherein the feature points contained in the feature point set are feature points located in a preset distance range of the last determined target feature point and the last determined target feature point;

when the number of the target characteristic points meets a preset number, N target characteristic points are obtained, wherein N is equal to the preset number;

the positioning module is specifically configured to, when obtaining matching degrees of the feature points acquired at the current time and the key time and a target object in the map information according to the feature points acquired at the key time and the coordinates of the feature points acquired at the current time under the vehicle body coordinate system at the current time and the position of each particle, specifically:

and according to the coordinates of the N target characteristic points in the vehicle body coordinate system at the current moment and the position of each particle, obtaining the matching degree of the characteristic points acquired at the current moment and the key moment and the target object in the map information of the target area.

28. The apparatus according to claim 27, wherein the feature value of the feature point is obtained by an evaluation function, and the feature value is used for evaluating stability of the feature point.

29. The apparatus according to claim 27 or 28, wherein the target feature point is a feature point having a largest feature value among the feature points.

30. The apparatus of any one of claims 16-29, wherein the origin of the body coordinate system is located at any position on the vehicle.

31. A positioning device, comprising: a memory and at least one processor;

the memory to store program instructions;

the processor, configured to invoke program instructions in the memory, to perform the positioning method according to any one of claims 1 to 15.

32. A positioning system, comprising: a vehicle and an onboard sensing device;

the vehicle-mounted sensing device is mounted on the vehicle;

the vehicle for performing the positioning method according to any one of claims 1-15; or,

the vehicle-mounted sensing device is used for executing the positioning method according to any one of claims 1 to 16.

33. A readable storage medium, characterized in that the readable storage medium has stored thereon a computer program; the computer program, when executed, implements a positioning method as claimed in any one of claims 1-15.

Images